DSP algorithm for cough identification and counting

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Digital signal processing (DSP) is applied to the analysis of the acoustic properties of pathological cough sounds. This work emanates from a clinical study of asthmatic, cystic fibrosis and cryptogenic fibrosing alveolitis patients. The pathological vocalisations exhibit clinically inconsistent acoustic properties from one disease to another. We aim to analyse the individual cough characteristic to adapt a DSP algorithm for identifying particular coughs and distinguishing them from background noise over long periods. The application is to obtain long-term statistical measurements to allow objective assessment of the severity of cough. This will be used for comparing the effectiveness of various treatments as well as to study the physiological characteristic of pulmonary diseases. In this work, cough identification and counting algorithm has been developed to detect and count coughs characteristic of asthma. Its accuracy has been assessed. A sensitivity of 70.5% and specificity of 98.3% were achieved.

Bibliographical metadata

Original languageEnglish
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings|ICASSP IEEE Int Conf Acoust Speech Signal Process Proc
Place of PublicationUSA
PublisherIEEE
PagesIV/3891
Volume4
Publication statusPublished - 2002
Event2002 IEEE International Conference on Acoustic, Speech, and Signal Processing - Orlando, FL
Event duration: 1 Jul 2002 → …

Conference

Conference2002 IEEE International Conference on Acoustic, Speech, and Signal Processing
CityOrlando, FL
Period1/07/02 → …